© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126634
    Prev
    Next
    INDEX
    Explanations

    mentions of gaming systems or related hardware

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ly
    -0.08
    andes
    -0.07
    ouv
    -0.06
     g
    -0.06
    xo
    -0.06
     segment
    -0.06
     sim
    -0.06
     Gus
    -0.06
     —
    -0.06
     curl
    -0.05
    POSITIVE LOGITS
    êu
    0.09
     addCriterion
    0.08
    itty
    0.08
    ãĥ¼ãĥľ
    0.07
    rine
    0.07
    á»ĵi
    0.07
    é¡
    0.07
    atican
    0.07
    UnderTest
    0.07
    ActionCreators
    0.07
    Activations Density 0.002%

    No Known Activations